Smart home systems and their control methods, home appliances, control equipment

Abstract

This application discloses a smart home system and its control method, home appliances, and control device, relating to the field of smart home technology. The control method is applied to home appliances within a smart home system. The method includes: acquiring reference information, including user needs, environmental parameters, and operating parameters of the home appliances; determining a local control strategy based on the user needs, environmental parameters, and operating parameters of the home appliances; sending the local control strategy to the control device of the smart home system, so that the control device, based on the local control strategy and a thought chain framework, determines a global control strategy from the overall perspective of the smart home system, and deconstructs the global control strategy into sub-control instructions for the corresponding home appliances; and receiving and executing the sub-control instructions. This application can reduce the risk of operational delays in controlling home appliances within a smart home system and can improve the overall performance of the smart home system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart home, in particular to a smart home system, a control method thereof, a home appliance and a control device. BACKGROUND

[0002] At present, the smart home system has been widely applied.

[0003] In the related art, the smart home system usually communicates all home appliances in a home environment to a cloud server, and a user accesses the cloud server through a terminal (for example, a computer or a mobile phone) to realize remote control of each home appliance in the home environment.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art:

[0005] In the related art, all data collected by all home appliances in the smart home system need to be transmitted to the cloud server, and then a control instruction is obtained from the cloud server, which may cause operation delay in controlling the home appliances. In the related art, the control of the home appliances is based on a single or fixed control logic, and there is a lack of effective coordination mechanism among the home appliances, resulting in poor overall performance of the smart home system.

[0006] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present application, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] To have a basic understanding of some aspects of the disclosed embodiments, a brief overview is given below. The overview is not a comprehensive overview of the application, nor is it intended to identify key / important elements or delineate the scope of the embodiments. Instead, the overview is presented as a prelude to the detailed description below.

[0008] The embodiments of the present disclosure provide a smart home system, a control method thereof, a home appliance and a control device. The risk of operation delay in controlling the home appliances in the smart home system can be reduced, and the overall performance of the smart home system can be improved.

[0009] In some embodiments, the control method of the smart home system is applied to an electrical appliance of the smart home system, and the control method comprises: acquiring reference information, the reference information comprising user demand, environmental parameters and operation parameters of the electrical appliance; determining a local control strategy according to the user demand, the environmental parameters and the operation parameters of the electrical appliance; sending the local control strategy to a control device of the smart home system, so that the control device determines a global control strategy based on a thinking chain framework in the overall perspective of the smart home system according to the local control strategy, and decomposes the global control strategy into a sub-control instruction for the corresponding electrical appliance; and receiving and executing the sub-control instruction.

[0010] Optionally, the determining of the local control strategy according to the user demand, the environmental parameters and the operation parameters of the electrical appliance comprises: preprocessing the environmental parameters and the operation parameters of the electrical appliance to obtain reference data; and performing multi-round reasoning on the electrical appliance based on the user demand and the reference data by using an agent set on the electrical appliance to obtain the local control strategy for the electrical appliance.

[0011] Optionally, after receiving and executing the sub-control instruction, the control method further comprises: feeding back a result of executing the sub-control instruction to a user terminal and / or the control device.

[0012] Optionally, after feeding back the result of executing the sub-control instruction to the user terminal, the control method further comprises: receiving feedback data of the user; and optimizing the agent according to the feedback data by using a reinforcement learning algorithm.

[0013] In some embodiments, the control method of the smart home system is applied to a control device of the smart home system, and the control method comprises: receiving a local control strategy sent by an electrical appliance; integrating all the received local control strategies to obtain global decision input; dividing the global decision input into multiple sub-tasks by using a thinking chain framework, and performing reasoning on the multiple sub-tasks with a first set requirement as a reasoning target to obtain a global control strategy; decomposing the global control strategy into a sub-control instruction, and sending the sub-control instruction to the corresponding electrical appliance.

[0014] Optionally, the performing of the reasoning on the multiple sub-tasks with the first set requirement as the reasoning target to obtain the global control strategy comprises: performing sequential reasoning or parallel reasoning on the multiple sub-tasks with the first set requirement as the reasoning target to obtain multiple initial control strategies; wherein each initial control strategy represents a group of control schemes for the electrical appliance and a predicted result of executing the control scheme; and each initial control strategy is evaluated, and an initial control strategy that meets the first set requirement and can maximize the satisfaction of a second set requirement is taken as the global control strategy.

[0015] Optionally, the control method of the smart home system further comprises: obtaining an execution result of the sub-control instruction fed back by the home appliance; sending the execution result and the global control strategy to the user terminal, and receiving feedback data of the user.

[0016] In some embodiments, the home appliance comprises a first processor and a second memory storing program instructions, the first processor is configured to execute the control method of the smart home system applied to the home appliance as described above when running the program instructions.

[0017] In some embodiments, the control device comprises a second processor and a second memory storing program instructions, the second processor is configured to execute the control method of the smart home system applied to the control device as described above when running the program instructions.

[0018] In some embodiments, the smart home system comprises: a plurality of home appliances as described above; and a control device as described above, which is in communication connection with the plurality of home appliances.

[0019] The smart home system and the control method thereof, the home appliance, and the control device provided by the embodiments of the present disclosure can achieve the following technical effects:

[0020] In the embodiments of the present disclosure, the smart home system comprises a plurality of home appliances and a control device in communication connection with the plurality of home appliances, and the control device is arranged in a home environment corresponding to the smart home system. In the process of controlling the home appliances in the smart home system, after the home appliances determine the local control strategy based on the obtained reference information (user demand, environmental parameter, and operation parameter of the home appliance), the local control strategy is sent to the control device, and the sub-control instruction required to be executed is obtained. In this way, when the home appliances in the smart home system are controlled, all data does not need to be uploaded to the cloud server, and since the control device is arranged in the home environment, the control device only provides services for this home environment, and the dependence on the network is low, and the control device also does not need to wait in line for task processing. Therefore, the embodiments of the present disclosure can reduce the risk of operation delay in controlling the home appliances in the smart home system. When the control device determines the sub-control instruction of the corresponding home appliance, the control device determines the global control strategy in the overall perspective of the smart home system based on the local control strategy according to the thinking chain framework, and then deconstructs the global control strategy to obtain the sub-control instruction of the corresponding home appliance. In this way, the coordination mechanism between the home appliances in the smart home system is considered, and the linkage control of the home appliances in the smart home system is realized. Therefore, the embodiments of the present disclosure can improve the overall performance of the smart home system.

[0021] The general description above and the following description below are exemplary and explanatory only and are not restrictive of the application. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the accompanying drawings required to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0024] Figure 1 is a schematic diagram of a smart home system provided by an embodiment of the present disclosure;

[0025] Figure 2 is a schematic diagram of a control method of a smart home system provided by an embodiment of the present disclosure;

[0026] Figure 3 is a schematic diagram of another control method of a smart home system provided by an embodiment of the present disclosure;

[0027] Figure 4 is a schematic diagram of another control method of a smart home system provided by an embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram of another control method of a smart home system provided by an embodiment of the present disclosure;

[0029] Figure 6 is a schematic diagram of a home appliance provided by an embodiment of the present disclosure;

[0030] Figure 7 is a schematic diagram of a control device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] In order to make the technical personnel in the art better understand the present application scheme, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort shall fall within the scope of protection of the present application.

[0032] It is to be understood that the terms "first", "second", and the like, used in the description and the claims of the present application as well as the above description of the drawings merely refer to structure which is different, and not necessarily to a specific order or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances. Also, the terms "comprise", "comprising", and the like, are to be construed as in the sense of "including" rather than in the sense of "consisting only of", and are intended to cover the process, method, system, product, or apparatus as well as its equivalents.

[0033] According to an aspect of embodiments of the present disclosure, a control method of a smart home system is provided. The smart home system includes a plurality of home appliances and a control device communicatively connected with the plurality of home appliances. The control method is applied to a home appliance or a control device of the smart home system, and can be applied to a home appliance or a control device of a smart home, a smart home device ecosystem, an intelligence house ecosystem, or the like.

[0034] In some embodiments, the above-described smart home system 10 is composed of a plurality of home appliances 100 and a control device 200, as shown in FIG. 1. Figure 1 As shown in FIG. 1, the plurality of home appliances 100 are connected to the central device 200 through a network, and thus the plurality of home appliances 100 can transmit a local control strategy to the control device 200 through the network and receive a sub control instruction from the control device 200 through the network. Figure 1

[0035] The above-described network can include, but is not limited to, at least one of a wired network and a wireless network. The above-described wired network can include, but is not limited to, at least one of a wide area network, a metropolitan area network, and a local area network, and the above-described wireless network can include, but is not limited to, at least one of WIFI (Wireless Fidelity) and Bluetooth.

[0036] ​The household appliance 100 in the smart home system 10, the smart home system, the smart home device ecosystem, and the smart home ecosystem includes a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart television, a smart clothesline, a smart curtain, a smart audio and video, a smart socket, a smart sound, a smart sound box, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, and a smart door lock, but is not limited thereto.

[0037] Optionally, each household appliance is provided with a communication interface, an agent, a data acquisition device, and a reinforcement learning module. The communication interface is used to receive user demand. The data acquisition device is used to acquire operating parameters and environmental parameters of the household appliance. The agent is used to determine a local control strategy for the household appliance according to the user demand, the environmental parameters, and the operating parameters of the household appliance. The reinforcement learning module is connected with the agent and is used to optimize an AI model in the agent by using a reinforcement learning algorithm.

[0038] Optionally, the control device is provided with a global decision-making module. The global decision-making module is used to determine a global control strategy by using a thinking chain framework according to the uploaded local control strategies of the household appliances, and decompose the global control strategy into control instructions for each household appliance, so as to control each household appliance to operate according to the control instructions.

[0039] In some embodiments, any one of the household appliances 100 in the smart home system 10 includes a first processor.

[0040] Optionally, the first processor can acquire reference information (the reference information includes user demand, environmental parameters, and operating parameters of the household appliance), and can determine a local control strategy according to the user demand, the environmental parameters, and the operating parameters of the household appliance. The local control strategy can be sent to a control device of the smart home system, so that the control device determines a global control strategy based on a thinking chain framework in the overall perspective of the smart home system according to the local control strategy, and decomposes the global control strategy into sub-control instructions for the corresponding household appliance. The sub-control instructions can be received and executed.

[0041] In combination with the above household appliance, the embodiments of the present disclosure provide a control method of a smart home system. The control method is applied to a household appliance of the smart home system, as shown in Figure 2 The control method includes the following steps.

[0042] S201, a first processor acquires reference information. The reference information includes user demand, environmental parameters, and operating parameters of the household appliance.

[0043] Specifically, the user demand represents a requirement raised by the user to the smart home system, for example, increasing the brightness in the room, reducing the temperature in the room, reducing the humidity in the room, and reducing the noise in the room, etc.

[0044] Specifically, the user demand can be input through a user terminal, a man-machine interaction interface on the household appliance, or a man-machine interaction interface on the control device, or can be judged by the household appliance through detection of user body information and environmental parameters.

[0045] Specifically, the user can raise the user demand to the smart home system through a terminal device that can be communicatively connected to the household appliance or the control device through a user interface, or can directly input the demand through a man-machine interaction interface on the household appliance or the control device. Since the first processor is arranged on the household appliance and the household appliance is communicatively connected to the control device, the first processor can obtain the user demand.

[0046] Specifically, each household appliance on the smart home system is provided with sensors of various parameters, which can be used to detect the user's body information in the room and the environmental data in the room, and the user demand can be judged according to the user's body information and the environmental data. Therefore, the first processor can obtain the user demand.

[0047] Specifically, the household appliance is provided with sensors that can sense the running condition of the household appliance and the environmental parameters of the environment in which the household appliance is located. Therefore, the first processor can obtain the environmental parameters and the running parameters of the household appliance through the sensors arranged on the household appliance.

[0048] S202, the first processor determines a local control strategy according to the user demand, the environmental parameters, and the running parameters of the household appliance.

[0049] Specifically, according to the user demand, it can be determined how to control the household appliance. For example, the user demand is to increase the brightness in the room, and it can be determined that the light device needs to be controlled to increase the brightness. For another example, the user demand is to reduce the temperature in the room, and it can be determined that the air conditioning device needs to be controlled to start or to reduce the cooling temperature and increase the air volume. According to the environmental parameters and the running parameters of the household appliance, the current state of the room and the current running state of the household appliance can be determined, so that the specific scheme of controlling the household appliance can be determined. For example, the temperature in the room is 28℃, the user demand temperature is 24℃, and the current cooling temperature of the air conditioning device is 28℃, so the local control strategy can be determined as reducing the cooling temperature of the air conditioning device by 4℃. Therefore, the first processor can determine the local control strategy according to the user demand, the environmental parameters, and the running parameters of the household appliance.

[0050] S203, the first processor sends the local control strategy to a control device of the smart home system, so that the control device determines a global control strategy based on the local control strategy and from the perspective of the whole smart home system based on the Chain of Thoughts (CoT) framework, and decomposes the global control strategy into sub-control instructions for corresponding home appliance devices.

[0051] Specifically, the control device is provided with a global decision module constructed based on the Chain of Thoughts (CoT) framework. The global decision module can determine a control scheme (i.e., the global control strategy) for the home appliance devices in the smart home system from the perspective of the whole smart home system according to the received local control strategy. In the global control strategy, the control scheme for the home appliance devices sending the local control strategy is not limited, and the control scheme for other devices can also be included. For example, the local control strategy sent by the lighting device is to increase the brightness of the lighting device to 80%. After the global decision module of the control device analyzes the working states of all home appliance devices in the smart home system based on the Chain of Thoughts framework, it is found that the curtains in the room are in a closed state, and the global control strategy obtained by the global decision module can be: open the curtains and increase the brightness of the lighting device to 60%. In this way, there is an effective coordination mechanism between the control of various home appliance devices in the smart home system, which facilitates the improvement of the overall performance of the smart home system.

[0052] Specifically, since the global control strategy can include control schemes for multiple home appliance devices, after the control device analyzes the local control strategy based on the Chain of Thoughts framework to obtain the global control strategy, the global control strategy needs to be decomposed to obtain one or more sub-control instructions. For example, the global control strategy is to open the curtains and increase the brightness of the lighting device to 60%. Decomposing the global control strategy can obtain two sub-control instructions, which are to control the curtains to open and to control the brightness of the lighting device to increase to 60%, respectively.

[0053] S204, the first processor receives and executes the sub-control instructions.

[0054] Specifically, after the home appliance devices receive the sub-control instructions, they act according to the corresponding sub-control instructions, so that the environment in the room meets the user's demand.

[0055] In the embodiments of the present disclosure, in the process of controlling the home appliances in the smart home system, after the home appliances determine the local control strategy based on the acquired reference information (user demand, environmental parameters and operation parameters of the home appliances), the local control strategy is sent to the control device, and the sub-control instruction to be executed by the home appliances can be obtained. In this way, when the home appliances in the smart home system are controlled, all data does not need to be uploaded to the cloud server, and since the control device is arranged in the home environment, the control device only provides services for this home environment, and the dependence on the network is low, and there is no need to wait in line for task processing. Therefore, the embodiments of the present disclosure can reduce the risk of operation delay of the control of the home appliances in the smart home system. When the control device determines the sub-control instruction of the corresponding home appliance, the control device determines the global control strategy in the overall perspective of the smart home system based on the local control strategy according to the thinking chain framework, and then deconstructs the global control strategy to obtain the sub-control instruction of the corresponding home appliance. In this way, the coordination mechanism between the home appliances in the smart home system is considered, and the linkage control of the home appliances in the smart home system is realized. Therefore, the embodiments of the present disclosure can improve the overall performance of the smart home system.

[0056] In addition, it also needs to be pointed out that, in the scheme of the related art, all data in the smart home system needs to be uploaded to the cloud server, which may exist the risk of leakage of user privacy data. In the embodiments of the present disclosure, only the local control strategy is sent to the control device, and the control device only provides services for the home environment in which the control device is located. Therefore, the embodiments of the present disclosure can also reduce the risk of leakage of user privacy data.

[0057] The embodiments of the present disclosure provide another control method of a smart home system, which is applied to a home appliance in the smart home system, such as Figure 3 As shown in the figure, the control method comprises:

[0058] S301, a first processor acquires reference information, and the reference information comprises user demand, environmental parameters and operation parameters of the home appliance.

[0059] S302, the first processor pre-processes the environmental parameters and the operation parameters of the home appliance to obtain reference data.

[0060] It can be understood that there may be noise data and error data in the collected environmental parameters and operation parameters of the home appliance, and these data may cause errors in the determined local control strategy. Therefore, the first processor needs to pre-process the environmental parameters and the operation parameters of the home appliance to obtain high-quality reference data.

[0061] Specifically, the preprocessing of the environmental parameters and the operation parameters of the home appliances includes, but is not limited to, cleaning processing (excluding error information or insignificant information in the environmental parameters and the operation parameters of the home appliances), normalization processing (unifying the dimensions of the environmental parameters and the operation parameters of the home appliances to facilitate subsequent calculation), standardization processing (eliminating the magnitude difference of the environmental parameters and the operation parameters of the home appliances and standardizing the distribution), and the like.

[0062] S303, the first processor obtains a local control strategy for the home appliance by using the agent set on the home appliance to perform multi-round reasoning based on the user demand and the reference data.

[0063] Specifically, each home appliance of the smart home system is correspondingly provided with an agent, and a multi-round reasoning generative AI model is constructed in each agent. The multi-round reasoning generative AI model is trained by a machine learning algorithm, and the AI model can perform multi-round reasoning based on the collected user demand, environmental parameters and operation parameters of the home appliance, and generate a local control strategy accordingly.

[0064] For example, taking the user's demand of improving the brightness in the room as an example, the multi-round reasoning of the agent to determine the local control strategy for the home appliance is exemplarily described as follows:

[0065] In the first round of reasoning, the agent can first compare the current environmental light parameters and the user demand. If the current indoor brightness is dark and lower than the user's expected target, it is determined that the local control strategy is to increase the light brightness.

[0066] In the second round of reasoning, the agent can consider historical data and user habits. For example, the historical data shows that the user prefers soft light in a specific situation (such as watching TV at night), so although it is considered from the perspective of environmental parameters that the light brightness needs to be improved to meet the user's needs, the light brightness should not be excessively increased to break the soft light environment atmosphere.

[0067] In the third round of reasoning, the agent can consider the mutual influence with other devices such as curtains. For example, if the curtain is in a closing state, the agent can draw a local control strategy of first opening the curtain to use natural light source and then appropriately increasing the brightness of the light device.

[0068] S304, the first processor sends the local control strategy to the control device of the smart home system, so that the control device determines a global control strategy in the overall perspective of the smart home system based on the thought chain framework according to the local control strategy, and decomposes the global control strategy into sub-control instructions for the corresponding home appliances.

[0069] S305, the first processor receives and executes the sub-control instructions.

[0070] In the embodiments of the present disclosure, the multi-round reasoning generative AI technology is adopted in the process of determining the local control strategy of the household appliance, thereby improving the accuracy of the determined local control strategy, improving the accuracy of the global control strategy determined based on the local control strategy, and improving the accuracy of the action of the household appliance.

[0071] In some embodiments, after receiving and executing the sub-control instruction, the control method further comprises: feeding back the result of executing the sub-control instruction to the user terminal and / or the control device.

[0072] Specifically, by feeding back the result of executing the sub-control instruction to the user terminal and / or the control device, the user can be made to know whether the demand raised by the user is met, and can timely feed back to the household appliance or the control device if the demand is not met. In this way, the user experience is improved. In some embodiments, after feeding back the result of executing the sub-control instruction to the user terminal, the control method further comprises: receiving feedback data of the user; and optimizing the agent by using a reinforcement learning algorithm according to the feedback data.

[0073] Specifically, reinforcement learning is a machine learning algorithm, the main idea of which is to make the agent on the household appliance learn an optimal strategy through trial and error and feedback in interaction with the environment, so that the cumulative reward obtained by the agent is maximized, thereby enabling the agent to derive a local control strategy with high accuracy.

[0074] Specifically, by using the reinforcement learning algorithm, the multi-round reasoning generative AI model in the agent can learn the feedback data of the user, thereby adjusting the standard for generating the local control strategy by the agent. For example, if the user feeds back in the feedback data that the brightness in the room is still too dark, it proves that the agent reasons that the adjustment amplitude of the local control strategy for the light brightness is low. Therefore, the standard for generating the local control strategy by the agent needs to be adjusted, so that the agent can increase the adjustment amplitude of the light device in the local control strategy given this time in the same or similar situation next time.

[0075] In the embodiments of the present disclosure, the agent of the household appliance is optimized by using the reinforcement learning algorithm, the agent can learn from the feedback data and improve its ability to adapt to the environment, and then adjust the standard for generating the local control strategy according to the feedback data. In this way, the agent can provide more accurate local control strategies in the future.

[0076] In some embodiments, the control device 200 in the smart home system comprises a second processor.

[0077] Optionally, the second processor can integrate all the local control strategies sent by the received home appliances to obtain a global decision input. The global decision input can be divided into multiple sub-tasks by using a thinking chain framework, and the multiple sub-tasks can be reasoned with the first set requirement as a reasoning target to obtain a global control strategy.

[0078] In combination with the above control device, the embodiments of the present disclosure provide a control method of a smart home system. The control method is applied to a control device of the smart home system, as shown in the above control device, and the control method comprises the following steps. Figure 4

[0079] S401, the second processor receives a local control strategy sent by a home appliance.

[0080] Specifically, the home appliance in this step can be one home appliance or multiple home appliances in the smart home system.

[0081] Specifically, the local control strategy needs to be represented in a structured data format, and needs to include the ID, device type, device state and control strategy of the home appliance and the like.

[0082] S402, the second processor integrates all the received local control strategies to obtain a global decision input.

[0083] Specifically, since the magnitudes of the local control strategies sent by different home appliances can be different, all the received local control strategies need to be integrated.

[0084] Optionally, integrating all the received local control strategies to obtain a global decision input comprises the following steps.

[0085] First, pre-process all the local control strategies.

[0086] Specifically, in order to ensure the consistency of the data formats of the local control strategies of different home appliances and the smoothness of the work of different home appliances, the local control strategies need to be pre-processed. The pre-processing can include formatting, normalization processing, and outlier rejection, so as to ensure that the data in all the local control strategies are within the same or similar range.

[0087] Second, integrate the pre-processed local control strategies.

[0088] Specifically, the local control strategies can be stored side by side by creating an Excel table or a database table to integrate the local control strategies.

[0089] Third, interpolate or fill in missing values for the integrated local control strategies.

[0090] ​Specifically, since in the embodiments of the present disclosure, the determination of the global control strategy needs to be made from the overall perspective of the smart home system. Therefore, when determining the global decision input, the current state of all appliances in the smart home system and the feedback of the execution result of the last action need to be determined. In some cases, there are situations where some appliances do not timely report the device state and the last action execution result feedback. Therefore, a reasonable placeholder needs to be created by using interpolation or missing value filling method to supplement, so as to maintain the integrity and continuity of the data.

[0091] Fourth, assigning a targeted weight to the integrated local control strategy.

[0092] Specifically, after determining the device state of all appliances in the smart home system, the running efficiency of the integrated local control strategy can be adjusted according to environmental parameters such as time and date, indoor and outdoor temperature and humidity, weather, and even the degree of electricity price fluctuation. The specific way can be to assign a targeted weight to different types of appliances and environmental impact factors. For example, during the hot summer, the weight of controlling the air conditioning device to run is higher than that of the television.

[0093] By determining the global decision input according to the above scheme, the CoT framework can subsequently find a global control decision that meets the user's demand, considers environmental factors, and optimizes the execution effect of the device.

[0094] S403, the second processor divides the global decision input into multiple sub-tasks using the thought chain framework, and reasons the multiple sub-tasks with the first set requirement as the reasoning target to obtain the global control strategy.

[0095] Specifically, the core idea of the thought chain framework is to simulate the human thinking process, divide the problem into multiple sub-problems, and gradually find a solution through one by one sub-problems, and consider various possible variables and their relationships in the process. This framework is very suitable for solving problems that need real-time processing and optimization in complex and variable environments. Therefore, the CoT framework is used in the embodiments of the present disclosure to reason the global decision input to determine the global control strategy.

[0096] Specifically, the first set requirement is the main requirement of the user for the overall performance of the smart home system, for example, improving the running efficiency of the appliances in the smart home system, reducing the energy consumption of the smart home system, etc.

[0097] Specifically, by dividing the global decision input into multiple sub-tasks, the multiple sub-tasks can be sequentially inferred or inferred in parallel with the first set requirement as the target, the solution of each sub-task is determined respectively, and by combining the solutions of the sub-tasks in different ways, multiple control strategies can be obtained, and the best control strategy that meets the first set requirement is selected from the multiple control strategies, that is, the global control strategy is obtained.

[0098] In S404, the second processor decomposes the global control strategy into sub-control instructions, and sends the sub-control instructions to the corresponding home appliance device.

[0099] Specifically, since the global control strategy can include a control scheme for multiple home appliance devices, after the control device obtains the global control strategy based on the analysis of the local control strategy by the thinking chain framework, the global control strategy needs to be decomposed to obtain one or more sub-control instructions. For example, the global control strategy is to open the curtain and increase the brightness of the light device to 60%, and the decomposition of the global control strategy can obtain two sub-control instructions, that is, to control the curtain to open and to control the brightness of the light device to increase to 60%.

[0100] In the embodiment of the present disclosure, when the control device determines the sub-control instructions for the home appliance device, the global control strategy is determined based on the local control strategy by the thinking chain from the overall perspective of the smart home system, and then the global control strategy is decomposed to obtain the sub-control instructions of the corresponding home appliance device. In this way, the coordination mechanism between the home appliance devices in the smart home system is considered, and the linkage control of the home appliance devices in the smart home system is realized. Therefore, the embodiment of the present disclosure can improve the overall performance of the smart home system.

[0101] The embodiment of the present disclosure provides a control method of a smart home system, which is applied to a control device of the smart home system, as shown in Figure 5 The control method comprises the following steps.

[0102] In S501, the second processor receives the local control strategy sent by the home appliance device.

[0103] In S502, the second processor integrates all the received local control strategies to obtain a global decision input.

[0104] In S503, the second processor sequentially infers or infers in parallel multiple sub-tasks with the first set requirement as the inference target, and obtains multiple initial control strategies.

[0105] Each initial control strategy represents a group of control schemes for the home appliance device and a predicted result of executing the control scheme.

[0106] Specifically, the plurality of sub-tasks are sequentially or in parallel inferred with the first set requirement as a target, and a solution of each sub-task is determined. The solutions of the sub-tasks are combined in different combinations, and a plurality of initial control strategies are obtained.

[0107] S504, the second processor evaluates each initial control strategy, and takes an initial control strategy that meets the first set requirement and can maximize the second set requirement as a global control strategy.

[0108] Specifically, the second set requirement is a secondary requirement for the overall performance of the smart home system, for example, user satisfaction, minimum number of household appliances running in the smart home system, etc.

[0109] Specifically, each initial control strategy can be evaluated based on the predicted results in each initial control strategy. After evaluation, the initial control strategies that can meet the first set requirement are sorted according to the degree of meeting the second set requirement, and the initial control strategy with the highest degree of meeting the second set requirement is selected as the global control strategy.

[0110] S505, the second processor decomposes the global control strategy into sub-control instructions, and sends the sub-control instructions to the corresponding household appliances.

[0111] In the embodiments of the present disclosure, when the global control strategy is confirmed, the initial control strategy that can maximize the second set requirement on the basis of meeting the first set requirement is selected as the global control strategy. This makes the global control strategy better meet the user's demand and improves the user's experience of using the smart home system.

[0112] In some embodiments, the control method further comprises: obtaining the execution result of the sub-control instruction fed back by the household appliance; sending the execution result and the global control strategy to the user terminal, and receiving the feedback data of the user.

[0113] Specifically, by sending the execution result of the sub-control instruction fed back by the household appliance and the determined global control strategy to the user terminal, the user can intuitively see whether the effect they expected has been successfully achieved, and understand the current running state of each household appliance. In this way, the user can choose whether to fine-tune the running mode of a certain household appliance, and give feedback and evaluation on the execution result of the household appliance, so as to optimize the agent of the household appliance according to the feedback data of the user in the future.

[0114] In combination Figure 6As shown, the embodiment of the present disclosure provides a home appliance 100, comprising: a first processor 601 and a second memory 602. Optionally, the home appliance 100 can further comprise a first communication interface 603 and a first bus 604. Wherein the first processor 601, the first communication interface 603, the memory 602 can complete the communication among each other through the first bus 604. The first communication interface 603 can be used for information transmission. The first processor 601 can call the logical instructions in the second memory 602 to execute the control method of the smart home system applied to the home appliance in the above-mentioned embodiment.

[0115] In addition, the logical instructions in the first memory 602 described above can be realized in the form of a software function unit and sold or used as an independent product when used, and can be stored in a computer readable storage medium.

[0116] The first memory 602 as a kind of computer readable storage medium can be used to store software programs, computer executable programs, such as the program instructions / modules corresponding to the method in the embodiment of the present disclosure. The first processor 601 executes the function application and data processing by running the program instructions / modules stored in the first memory 602, that is, realizes the control method of the smart home system applied to the home appliance in the above-mentioned embodiment.

[0117] The first memory 602 can include a storage program area and a storage data area, wherein the storage program area can store an operating system, at least one application required by a function; The storage data area can store data created according to the use of the terminal device and the like. In addition, the first memory 602 can include a high-speed random access memory, and can also include a non-volatile memory.

[0118] In combination Figure 7 As shown, the embodiment of the present disclosure provides a control device 100, comprising: a second processor 701 and a second memory 702. Optionally, the control device 100 can further comprise a second communication interface 703 and a second bus 704. Wherein the second processor 701, the second communication interface 703, the memory 702 can complete the communication among each other through the second bus 704. The second communication interface 703 can be used for information transmission. The second processor 701 can call the logical instructions in the second memory 702 to execute the control method of the smart home system applied to the control device in the above-mentioned embodiment.

[0119] In addition, the logic instructions in the second memory 702 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium.

[0120] The second memory 702 is a computer readable storage medium, which can be used to store software programs, computer executable programs, such as program instructions / modules corresponding to the method in the embodiments of the present disclosure. The second processor 701 executes the program instructions / modules stored in the second memory 702, thereby performing function applications and data processing, that is, implementing the control method of the smart home system applied to the control device in the above embodiments.

[0121] The second memory 702 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function; the data storage area can store data created according to the use of the terminal device, etc. In addition, the second memory 702 can include a high-speed random access memory, and can also include a non-volatile memory.

[0122] The embodiments of the present disclosure provide a computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are set to execute the control method of the smart home system.

[0123] The above only describes the preferred embodiments of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should be considered as the protection scope of the present application.

Claims

1. A control method of a smart home system, applied to a control device, the method comprising: receiving a voice input from a user; identifying a voice command included in the voice input; and controlling a device based on the identified voice command. The control method comprises: receiving local control strategies sent by the home appliances; integrating all the received local control strategies to obtain a global decision input; dividing the global decision input into multiple sub-tasks using a thinking chain framework, and reasoning the multiple sub-tasks with a first set requirement as a reasoning target to obtain a global control strategy; deconstructing the global control strategy into sub-control instructions, and sending the sub-control instructions to corresponding home appliances. 2.The control method of a smart home system according to claim 1, wherein, reasoning the multiple sub-tasks with the first set requirement as a reasoning target to obtain a global control strategy, comprising: sequentially or in parallel reasoning the multiple sub-tasks with the first set requirement as a reasoning target to obtain multiple initial control strategies; each initial control strategy represents a group of control schemes for the home appliances and a predicted result of executing the control schemes; evaluating each initial control strategy, and taking an initial control strategy that meets the first set requirement and can maximize the satisfaction of the second set requirement as the global control strategy. 3.The control method of a smart home system according to claim 1 or 2, characterized in that, further comprising: obtaining an execution result of the sub-control instructions fed back by the home appliances; sending the execution result and the global control strategy to a user terminal, and receiving feedback data of the user.

4. A control device comprising a second processor and a second memory storing program instructions, wherein, The second processor is configured to execute the control method of the smart home system according to any one of claims 1 to 3 when running the program instructions.

5. A smart home system, characterized by, comprise: a plurality of home appliances, which are configured to obtain reference information including user demand, environmental parameters and operation parameters of the home appliances, determine local control strategies according to the user demand, the environmental parameters and the operation parameters of the home appliances, send the local control strategies to a control device of a smart home system, so that the control device determines a global control strategy based on a thinking chain framework from the overall perspective of the smart home system according to the local control strategies, and deconstructs the global control strategy into sub-control instructions for corresponding home appliances, and receive and execute the sub-control instructions; the control device according to claim 4, which is in communication connection with the plurality of home appliances. 6.The smart home system according to claim 5, characterized in that, determining the local control strategies according to the user demand, the environmental parameters and the operation parameters of the home appliances, comprising: preprocessing the environmental parameters and the operation parameters of the home appliances to obtain reference data; based on the user demand and the reference data, performing multiple rounds of reasoning using an agent set on the home appliances to obtain the local control strategies for the home appliances. 7.The smart home system according to claim 5 or 6, characterized in that, after receiving and executing the sub-control instructions, the home appliances are further configured to: feed back a result of executing the sub-control instructions to a user terminal and / or the control device. 8.The smart home system according to claim 7, characterized in that, after feeding back the result of executing the sub-control instructions to the user terminal, the home appliances are further configured to: receive feedback data of the user; based on the feedback data, optimize the agent using a reinforcement learning algorithm.

Images